Using Maximal Embedded Syntatic Subtrees for Textual Entailment Recognition thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Using Maximal Embedded Syntatic Subtrees for Textual Entailment Recognition

Published on Feb 25, 20072942 Views

In this paper we address the textual entailment task by using tree mining and matching technique. Our results show that accuracy can be improved when using a combination of lexical entailment with syn

Chapter list

Using Maximal Embedded Subtrees for Textual Entailment Recognition00:01
Outline01:13
Why trees?…01:25
Motivation02:39
What type of trees? (1)03:07
What type of trees?(2)03:40
Methodology05:16
Data preprocessing05:38
Syntactic matching06:22
Runs07:02
Official results (accuracy)07:59
Precision vs. Recall08:22
Precision vs. Recall (2)09:02
Conclusions: Does it work? 09:37
Possible extensions10:07
slide1610:27